Artificial intelligence as a clinical decision support tool in the diagnosis and treatment of inflammatory dermatoses

Artificial intelligence (AI) in dermatovenereology has, in recent years, evolved from an experimental concept into an effective tool for clinical decision support. Modern algorithms demonstrate high diagnostic accuracy in the recognition of skin neoplasms and inflammatory dermatoses, and their use by physicians improves the sensitivity and specificity of diagnosis. AI is actively applied in the analysis of clinical images, teledermatology, confocal microscopy, and histological studies, enabling more objective assessment of skin lesions and monitoring of disease dynamics. AI is of particular importance in the management of patients with allergic dermatoses, where the clinical presentation is often complicated by secondary infection. Clinical decision support systems can detect microsigns of inflammation, assess the risks of bacterial and fungal complications, and recommend preventive therapeutic approaches. This facilitates earlier and more justified use of combination topical therapy. Combination preparations containing glucocorticosteroids, an antibiotic, and an antifungal agent allow simultaneous control of inflammation and the infectious component. The use of such agents as Akriderm GK demonstrates high clinical efficacy and rapid achievement of remission. The integration of AI into clinical practice improves diagnostic accuracy, accelerates therapeutic decision-making, and reduces the risk of complications. At the same time, the key role in decision-making remains with the physician, while AI serves as an adjunct tool that enhances clinical reasoning and improves the quality of medical care.

1. Vasilev YuA, Galkin VN, Ravodin RA, Nanova OG, Savin NA, Blokhin IA et al. Artificial intelligence in dermatology: а scoping review. Vestnik Dermatologii i Venerologii. 2025;101(6):9–21. (In Russ.) https://doi.org/10.25208/vdv16936.

2. Krakowski I, Kim J, Cai ZR, Daneshjou R, Lapins J, Eriksson H et al. Human-AI interaction in skin cancer diagnosis: a systematic review and meta-analysis. NPJ Digit Med. 2024;7(1):78. https://doi.org/10.1038/s41746-024-01031-w.

3. Liu D, Hu BD, Glickman J, O’Hagan R, He H, Guttman-Yassky E. Artificial intelligence in atopic dermatitis: A narrative review. J Allergy Clin Immunol. 2025;156(4):889–898. https://doi.org/10.1016/j.jaci.2025.06.028.

4. Кубанов АА, Намазова-Баранова ЛС, Волнухин ВА, Дворников АС, Ильина НИ, Заславский ДВ и др. Атопический дерматит: клинические рекомендации. М.; 2024. 100 с. Режим доступа: https://cr.minzdrav.gov.ru/view-cr/265_3.

5. Cao F, Yang Y, Guo C, Zhang H, Yu Q, Guo J. Advancements in artificial intelligence for atopic dermatitis: diagnosis, treatment, and patient management. Ann Med. 2025;57(1):2484665. https://doi.org/10.1080/07853890.2025.2484665.

6. Кубанов АА, Намазова-Баранова ЛС, Баранов АА, Хаитов МР, Потекаев НН, Амбарчян ЭТ и др. Дерматит контактный: клинические рекомендации. М.; 2024. 46 с. Режим доступа: http://cr.minzdrav.gov.ru/view-cr/213_3.

7. Намазова-Баранова ЛС, Баранов АА, Алексеева АА, Алексеева АД, Амбарчян ЭТ, Аникина ДД и др. Атопический дерматит: руководство для врачей. 3-е изд., обновл. М.: Педиатръ; 2025. 60 с. Режим доступа: https://www.elibrary.ru/gopgcx.

8. Потекаев НН, Акимов ВГ, Жукова ОВ, Кочетков МА. Дифференциальная диагностика и лечение кожных болезней: атлас-справочник. 2-е изд., перераб. и доп. М.: ГЭОТАР-Медиа; 2026. 456 с. https://doi.org/10.33029/9704-9658-9-DDD-2026-1-456.